---
title: "Slides: You Might Not Need 50 Diffusion Steps — Ziv Ilan, Nvidia"
category: "slides"
video_id: "gHs5ZiY80PM"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

# Slides: You Might Not Need 50 Diffusion Steps — Ziv Ilan, Nvidia

## Source Video
[You Might Not Need 50 Diffusion Steps — Ziv Ilan, Nvidia](https://www.youtube.com/watch?v=gHs5ZiY80PM)

## Relationship To World's Fair 2026
These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

## Related Scheduled Sessions
- No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.

## Extracted Slides
![[assets/slides/gHs5ZiY80PM/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/gHs5ZiY80PM/slide-002.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: agent_vision.
- OCR decision: ready — Dense bullets and small diagram labels are better handled by OCR than manual vision transcription.

Slide text:

> Diffusion models: What & Why

![[assets/slides/gHs5ZiY80PM/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/gHs5ZiY80PM/slide-003.html)
- AI slide classifier: `content_slide` confidence `0.99`
- Text source: advanced OCR `rapidocr-live/bright-screen/contrast`.
- OCR decision: ready — Mixed small captions, comparison images, and code-like text are OCR-suitable.

Slide text:

> Quantization: Performance & Quality
> FLUx2[dev]on Blackwell|Quaitypreserved ateveryprccision level
> 16 NM04 B16
> AIE
> DIY with TensorRT-LLM - Visual Gen Run a pre-quantized ckpt from HF
> #With NVFP4quantization labs/FLUx.2-dev --prompt "A cat' --linear_type trtllm-nvfp4 python visual_gen_flux.py--model_path black-forest- black-forest-labs/FLUX.2-dev-NVFP4
> WIGAA
> AI Engineer
> AlEnginecr EUROPE
> TUROK
> 20


### Hidden Non-Slide Evidence
- [`slide-001.jpg`](/assets/slides/gHs5ZiY80PM/slide-001.jpg) — `speaker_stage` confidence `0.98`; Speaker on stage with only a partially visible slide; not a readable presentation slide.

Classification audit: `raw/sources/slide-ai-classification/slides/gHs5ZiY80PM/audit.json`

## Slide-Derived Subjects To Review
Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.